browser-automation-notte
browser-automation-notte provides programmatic control over browser sessions for web automation, scraping, and AI agent deployment. Start sessions with custom configurations, execute page interactions, capture screenshots, and manage cookies and network logs. Run autonomous agents to complete complex browser tasks end-to-end.
browser-automation-notte lets you control browser sessions, scrape web pages, and run autonomous AI agents via API.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-23
browser-automation-notte lets you control browser sessions, scrape web pages, and run autonomous AI agents via API. browser-automation-notte provides programmatic control over browser sessions for web automation, scraping, and AI agent deployment. Start sessions with custom configurations, execute page interactions, capture screenshots, and manage cookies and network logs. Run autonomous agents to complete complex browser tasks end-to-end.
Use it when
- browser-automation-notte lets you manage and monitor browser sessions through its API.
- Yes, browser-automation-notte supports structured data extraction from web pages via scraping.
Verify before relying
Read SKILL.md below before installing (2 files). Open directory: indexed for reading, not audited.
Install
gooseworks-ai/goose-skills/browser-automation-notte · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is browser-automation-notte used for?
browser-automation-notte provides programmatic control over browser sessions for web automation, scraping, and AI agent deployment. You can start sessions with custom configurations, execute page interactions, capture screenshots, and manage cookies and network logs. The skill also enables you to run autonomous agents to complete complex browser tasks end-to-end.
How do I control browser sessions programmatically?
browser-automation-notte lets you manage and monitor browser sessions through its API. You can start sessions with custom configurations, execute interactions like clicks and typing, capture screenshots, and handle cookies and network logs programmatically. This gives you full programmatic control over your browser workflows.
Can browser-automation-notte extract data from websites?
Yes, browser-automation-notte supports structured data extraction from web pages via scraping. You can scrape page content, capture screenshots, and extract web page data programmatically. This makes it easy to gather information from websites automatically.
What is an autonomous web agent and how does it work?
browser-automation-notte enables you to deploy autonomous AI agents to complete browser workflows. These agents can execute complex web tasks end-to-end without manual intervention, handling interactions, data extraction, and navigation automatically based on your configuration.
Is browser-automation-notte suitable for web application testing?
Yes, browser-automation-notte supports automated browser actions for testing web applications. You can automate clicks, typing, and other interactions to validate application behavior, making it useful for test automation alongside its primary web automation and scraping capabilities.
What license does browser-automation-notte use?
browser-automation-notte is released under the MIT license, which permits free use, modification, and distribution with minimal restrictions.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Notte - Browser Automation API
Setup
Read your credentials from ~/.gooseworks/credentials.json:
export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")
If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login
All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"
Control browser sessions, scrape web pages, and run autonomous AI agents.
Capabilities
- Take Screenshot: Take a screenshot of the current page
- Get Session: Get session status and details (free)
- Stop Session: Stop and clean up a browser session (free)
- Get Session Cookies: Get all cookies from the browser session (free)
- Get Network Logs: Get network request/response logs from the session (free)
- Get Agent Status: Get agent
(truncated - see the full file via the links below)
File tree — 2 files
skills/research-tools/capabilities/browser-automation-notte/SKILL.md
skills/research-tools/capabilities/browser-automation-notte/skill.meta.json
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Automate browser interactions and web tasks with API control”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Restaurant Booking uses browser automation to complete dinner reservations across major platforms. It handles date/time selection, party size, guest details, and form submission to secure your table.
Web-scraping lets you pull structured data from any URL using plain English descriptions of what you need. Choose from AI-powered extraction with natural language prompts, high-volume batch processing, or schema-based data structuring—then combine methods for comprehensive site crawling and automation.
Website Screenshot Notte lets you grab visual snapshots of any webpage through Notte's browser automation. Start a session, navigate to your target URL, capture the viewport or full page, then stop—all via straightforward API calls. Customize viewport dimensions and choose headless or visible browsing.
web-search-exa provides neural search powered by embeddings to discover relevant web content, extract full page text, and synthesize findings. Query the web intelligently across multiple search modes, filter by domain or date, and get LLM-generated answers informed by live search results.
This skill harnesses AI to pull structured information from web pages by simply describing what you want. Use natural language prompts to extract product details, search results, or entire site content, with support for JavaScript-heavy sites, pagination, and custom output schemas.
LinkedIn Scraper pulls public profile data, company information, and posts directly from LinkedIn using full page URLs. Access professional details like names, headlines, education history, skills, and connection counts for individuals, plus company specifics such as industry, size, and employee count.
More skills instagram-scraper (MIT) · tiktok-search (MIT) · extract-webpage-data (MIT) · goose-graphics (MIT)